# UWFormer: Underwater Image Enhancement via a Semi-Supervised Multi-Scale Transformer

arXiv: https://arxiv.org/abs/2310.20210 · HTML: https://mlsanity.com/paper/2310.20210/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 62 references that are in the map.
- First posted on arXiv 31 Oct 2023.

## Builds on (most cited first, 26 of 26)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [Rethinking Coarse-to-Fine Approach in Single Image Deblurring](https://mlsanity.com/paper/2108.05054/) (2021)
- [Learning from Simulated and Unsupervised Images through Adversarial Training](https://mlsanity.com/paper/1612.07828/) (2016)
- [Multi-Scale Progressive Fusion Network for Single Image Deraining](https://mlsanity.com/paper/2003.10985/) (2020)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding](https://mlsanity.com/paper/2104.13015/) (2021)
- [Explicit Visual Prompting for Low-Level Structure Segmentations](https://mlsanity.com/paper/2303.10883/) (2023)
- [Enhancing Underwater Imagery using Generative Adversarial Networks](https://mlsanity.com/paper/1801.04011/) (2018)
- [Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions](https://mlsanity.com/paper/1901.05320/) (2019)
- [Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning](https://mlsanity.com/paper/2207.04978/) (2022)
- [Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank](https://mlsanity.com/paper/2303.09101/) (2023)
- [High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network](https://mlsanity.com/paper/2105.09188/) (2021)
- [DCSFN: Deep Cross-scale Fusion Network for Single Image Rain Removal](https://mlsanity.com/paper/2008.00767/) (2020)
- [High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net](https://mlsanity.com/paper/2308.14221/) (2023)
- [Shallow-UWnet : Compressed Model for Underwater Image Enhancement](https://mlsanity.com/paper/2101.02073/) (2021)
- [CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying](https://mlsanity.com/paper/2303.08524/) (2023)
- [A Large-scale Film Style Dataset for Learning Multi-frequency Driven Film Enhancement](https://mlsanity.com/paper/2301.08880/) (2023)
- [Brain Diffuser: An End-to-End Brain Image to Brain Network Pipeline](https://mlsanity.com/paper/2303.06410/) (2023)
- [Devignet: High-Resolution Vignetting Removal via a Dual Aggregated Fusion Transformer With Adaptive Channel Expansion](https://mlsanity.com/paper/2308.13739/) (2023)
- [MedPrompt: Cross-Modal Prompting for Multi-Task Medical Image Translation](https://mlsanity.com/paper/2310.02663/) (2023)
- [WavEnhancer: Unifying Wavelet and Transformer for Image Enhancement](https://mlsanity.com/paper/2212.08327/) (2022)

## Built on by (most cited first, 9 of 9)

- [Unified-EGformer: Exposure Guided Lightweight Transformer for Mixed-Exposure Image Enhancement](https://mlsanity.com/paper/2407.13170/) (2024)
- [High-Fidelity Functional Ultrasound Reconstruction via A Visual Auto-Regressive Framework](https://mlsanity.com/paper/2505.21530/) (2025)
- [AI-Driven Marine Robotics: Emerging Trends in Underwater Perception and Ecosystem Monitoring](https://mlsanity.com/paper/2509.01878/) (2025)
- [Underwater Image Enhancement using Generative Adversarial Networks: A Survey](https://mlsanity.com/paper/2501.06273/) (2025)
- [ConnectomeDiffuser: Generative AI Enables Brain Network Construction from Diffusion Tensor Imaging](https://mlsanity.com/paper/2505.22683/) (2025)
- [Brain Network Analysis Based on Fine-tuned Self-supervised Model for Brain Disease Diagnosis](https://mlsanity.com/paper/2506.11671/) (2025)
- [Excavate the potential of Single-Scale Features: A Decomposition Network for Water-Related Optical Image Enhancement](https://mlsanity.com/paper/2508.04123/) (2025)
- [SFormer: SNR-guided Transformer for Underwater Image Enhancement from the Frequency Domain](https://mlsanity.com/paper/2508.18664/) (2025)
- [Retinex Meets Language: A Physics-Semantics-Guided Underwater Image Enhancement Network](https://mlsanity.com/paper/2603.07076/) (2026)

## Abstract (arXiv)

Underwater images often exhibit poor quality, distorted color balance and low contrast due to the complex and intricate interplay of light, water, and objects. Despite the significant contributions of previous underwater enhancement techniques, there exist several problems that demand further improvement: (i) The current deep learning methods rely on Convolutional Neural Networks (CNNs) that lack the multi-scale enhancement, and global perception field is also limited. (ii) The scarcity of paired real-world underwater datasets poses a significant challenge, and the utilization of synthetic image pairs could lead to overfitting. To address the aforementioned problems, this paper introduces a Multi-scale Transformer-based Network called UWFormer for enhancing images at multiple frequencies via semi-supervised learning, in which we propose a Nonlinear Frequency-aware Attention mechanism and a Multi-Scale Fusion Feed-forward Network for low-frequency enhancement. Besides, we introduce a special underwater semi-supervised training strategy, where we propose a Subaqueous Perceptual Loss function to generate reliable pseudo labels. Experiments using full-reference and non-reference underwater benchmarks demonstrate that our method outperforms state-of-the-art methods in terms of both quantity and visual quality.